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. 111564
    Prev
    Next
    INDEX
    Explanations

    Lincoln

    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
     Hoch
    -0.08
    က္
    -0.08
    �
    -0.08
    �
    -0.07
    Touches
    -0.07
    ুলো
    -0.07
    醒
    -0.07
     Gabe
    -0.07
     Mein
    -0.07
    ్ప
    -0.07
    POSITIVE LOGITS
    shire
    0.10
    XM
    0.08
     wings
    0.08
     superintendent
    0.07
     monop
    0.07
    mad
    0.07
     Manc
    0.07
    .Le
    0.07
     tient
    0.07
     tendencies
    0.07
    Activations Density 0.003%

    No Known Activations