© 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. 129346
    Prev
    Next
    INDEX
    Explanations

    Cyrillic characters

    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
    ic
    -0.08
     muri
    -0.08
    Intr
    -0.07
    flu
    -0.07
    pf
    -0.07
    outin
    -0.07
    _secondary
    -0.07
    icl
    -0.07
    Frm
    -0.07
    VB
    -0.07
    POSITIVE LOGITS
     माना
    0.09
     priori
    0.08
     значение
    0.08
     образование
    0.07
     число
    0.07
     решение
    0.07
     بہ
    0.07
     боль
    0.07
     окно
    0.07
     ون
    0.07
    Activations Density 0.026%

    No Known Activations