© 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. 218
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    费
    -0.08
    ทั่ว
    -0.08
    平县
    -0.08
     Ll
    -0.08
    azwa
    -0.07
     Fund
    -0.07
     Enkel
    -0.07
     ava
    -0.07
    แพ
    -0.07
     Christians
    -0.07
    POSITIVE LOGITS
    ESC
    0.08
    oor
    0.07
    /*
    0.07
    rd
    0.07
    _CONF
    0.07
     /*
    0.07
     разг
    0.07
    screen
    0.07
    \,
    0.07
     thes
    0.07
    Activations Density 0.022%

    No Known Activations