© 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. 102868
    Prev
    Next
    INDEX
    Explanations

    say "= symbol"

    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
     unsure
    -0.10
     wasu
    -0.09
     nifer
    -0.09
     alcuni
    -0.09
     bazı
    -0.09
     alguns
    -0.09
     ------------------------------------------------------------------------------------------------
    -0.09
     birnäçe
    -0.09
    gunos
    -0.08
     někter
    -0.08
    POSITIVE LOGITS
     =
    0.12
    =$
    0.11
    =user
    0.11
    =args
    0.11
    ']=$
    0.10
    '=>$
    0.10
    =${
    0.10
    =r
    0.10
    =text
    0.10
    .↵↵
    0.10
    Activations Density 0.005%

    No Known Activations