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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29620
    Prev
    Next
    INDEX
    Explanations

    mathematical functions

    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
    HOR
    -0.08
     importantly
    -0.08
    Hor
    -0.08
     whatever
    -0.07
    Kath
    -0.07
     waters
    -0.07
    程度
    -0.07
    verting
    -0.07
     chopping
    -0.07
     ballast
    -0.07
    POSITIVE LOGITS
    :Boolean
    0.09
    .rank
    0.08
     Looks
    0.08
     Warp
    0.08
    ){
    0.08
     Rank
    0.08
    "){
    0.08
     ::=
    0.08
     jechuun
    0.08
     laz
    0.07
    Activations Density 0.049%

    No Known Activations