© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95614
    Prev
    Next
    INDEX
    Explanations

    Skipping something

    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
     applause
    -0.08
     Bann
    -0.08
    weisung
    -0.07
     enumerate
    -0.07
     enum
    -0.07
    აჭ
    -0.07
     clearer
    -0.07
     গোল
    -0.07
     �
    -0.07
    iening
    -0.07
    POSITIVE LOGITS
     hábitos
    0.10
     habits
    0.10
     hábito
    0.09
     procrast
    0.09
     shortcuts
    0.09
    省
    0.08
     않아
    0.08
    ేస్త
    0.08
     ahorrar
    0.08
     consciously
    0.08
    Activations Density 0.113%

    No Known Activations