© 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. 51435
    Prev
    Next
    INDEX
    Explanations

    say "/"

    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
    =%
    -0.09
    ='
    -0.08
    usr
    -0.08
    subset
    -0.08
    ='%
    -0.07
    ROP
    -0.07
    NUM
    -0.07
    -full
    -0.07
    activity
    -0.07
    chemical
    -0.07
    POSITIVE LOGITS
    キー
    0.09
    \Json
    0.08
     kvin
    0.08
     JSONArray
    0.08
     тей
    0.08
     JSONObject
    0.08
    \v
    0.08
    >An
    0.07
    zki
    0.07
    냥
    0.07
    Activations Density 0.002%

    No Known Activations