© 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 EvalsExportsAPI 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. 69195
    Prev
    Next
    INDEX
    Explanations

    mathematical indices

    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
     Ruiz
    -0.08
     ruhig
    -0.08
     bünd
    -0.08
    isissez
    -0.08
    ុល
    -0.08
    lebnis
    -0.08
     ரூ
    -0.08
     Amm
    -0.08
    'imm
    -0.07
    {sub
    -0.07
    POSITIVE LOGITS
     reversed
    0.11
    Reverse
    0.11
     reverse
    0.11
     reversal
    0.10
    reverse
    0.10
     revers
    0.10
     reversing
    0.10
     backwards
    0.10
     Reverse
    0.10
    .reverse
    0.09
    Activations Density 0.046%

    No Known Activations