© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 111113
    Prev
    Next
    INDEX
    Explanations

    Legal/academic arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -launch
    -0.10
    Launch
    -0.09
     launches
    -0.09
    -paced
    -0.08
    .drive
    -0.08
    everyone
    -0.08
     Launch
    -0.08
     قيادة
    -0.08
    _launch
    -0.08
     Tenerife
    -0.08
    POSITIVE LOGITS
     litig
    0.15
     litigation
    0.14
     अदालत
    0.13
     unconstitutional
    0.13
     appellate
    0.13
     আদাল
    0.13
    法院
    0.13
     plaintiffs
    0.13
     judgments
    0.12
     நீத
    0.12
    Activations Density 0.068%

    No Known Activations