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. 55685
    Prev
    Next
    INDEX
    Explanations

    prose

    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
     göt
    -0.08
     obtains
    -0.08
     previo
    -0.08
     previamente
    -0.08
    totime
    -0.08
     abusing
    -0.08
     preg
    -0.08
    оч
    -0.08
     disputa
    -0.07
    前年
    -0.07
    POSITIVE LOGITS
    —↵↵
    0.07
    ाट
    0.07
    insk
    0.07
    —
    0.07
     מוס
    0.07
    -ed
    0.07
     Conn
    0.07
    ’re
    0.07
    (email
    0.07
    ouveau
    0.07
    Activations Density 0.408%

    No Known Activations