© 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. 19-RESID-POST-AA
    11. 18942
    Prev
    Next
    INDEX
    Explanations

    :

    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
     unik
    -0.08
    [h
    -0.08
    [start
    -0.08
    #ifndef
    -0.08
    ’éviter
    -0.08
    และ
    -0.07
    和
    -0.07
     and
    -0.07
    [random
    -0.07
    -0.07
    POSITIVE LOGITS
    
    0.09
     يبلغ
    0.09
     incorporates
    0.08
     составляет
    0.08
     proposes
    0.08
    �
    0.08
    ercicio
    0.08
    atha
    0.08
     має
    0.08
     Determines
    0.08
    Activations Density 0.000%
    No Known Activations