© 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. 19-RESID-POST-AA
    11. 103143
    Prev
    Next
    INDEX
    Explanations

    Technical network specifications

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     by
    -0.08
    /.
    -0.08
     as
    -0.08
     phenomenon
    -0.08
     {
    -0.08
     =
    -0.07
     habitu
    -0.07
     =~
    -0.07
     dėl
    -0.07
     //
    -0.07
    POSITIVE LOGITS
    送りします
    0.10
    Networking
    0.09
     escribir
    0.08
    絡
    0.08
     commissioners
    0.08
    ocked
    0.08
     ಬರ
    0.08
    ଧ
    0.08
    Washington
    0.08
     bites
    0.08
    Activations Density 0.000%

    No Known Activations