Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 246
    Prev
    Next
    INDEX
    Explanations

    Carrying items

    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
    说道
    -0.09
    ദ്ധ
    -0.08
     Reynolds
    -0.08
    SOLE
    -0.08
     anschauen
    -0.08
    _AST
    -0.08
    eree
    -0.07
     vlag
    -0.07
     Facil
    -0.07
    tur
    -0.07
    POSITIVE LOGITS
     invis
    0.08
    Shadow
    0.08
     ежеднев
    0.08
     постоян
    0.08
     항상
    0.08
     prayers
    0.08
     sehari
    0.07
     jewelry
    0.07
     常
    0.07
    随
    0.07
    Activations Density 0.016%

    No Known Activations