© 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. 11-RESID-POST-AA
    11. 129498
    Prev
    Next
    INDEX
    Explanations

    Foreign characters/symbols

    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
    sns
    -0.08
    र्शन
    -0.08
     Endless
    -0.08
     ekz
    -0.08
    yscr
    -0.08
    funnels
    -0.07
    .roll
    -0.07
     конеч
    -0.07
     @$
    -0.07
    ാത്ര
    -0.07
    POSITIVE LOGITS
    AVL
    0.08
     verso
    0.08
     halfway
    0.08
     uses
    0.08
     odi
    0.07
    辱
    0.07
     пораж
    0.07
    ）、
    0.07
    _vlan
    0.07
     confund
    0.07
    Activations Density 0.015%

    No Known Activations