© 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. 23-RESID-POST-AA
    11. 51010
    Prev
    Next
    INDEX
    Explanations

    say ".g" suffix

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invloed
    -0.09
     ترقی
    -0.09
    ahusay
    -0.08
    igs
    -0.08
    volution
    -0.08
     wasu
    -0.08
    akisa
    -0.08
     spu
    -0.08
    �
    -0.08
     conjuntos
    -0.08
    POSITIVE LOGITS
     punctuation
    0.14
    OL
    0.13
    ol
    0.11
     ol
    0.10
     uppercase
    0.10
     OL
    0.10
     "\
    0.10
    ofanira
    0.10
    _sentence
    0.10
    _letter
    0.09
    Activations Density 0.018%

    No Known Activations