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. 23729
    Prev
    Next
    INDEX
    Explanations

    cross product

    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
     [+
    -0.07
    Deliver
    -0.07
     denying
    -0.07
     ulcer
    -0.07
    _STOP
    -0.07
     läm
    -0.07
    	http
    -0.07
    Dial
    -0.07
    Bak
    -0.07
    .db
    -0.07
    POSITIVE LOGITS
     hull
    0.08
    obr
    0.08
     সাধ
    0.08
     দলের
    0.08
     Esq
    0.08
    -valu
    0.07
    maya
    0.07
     Women's
    0.07
    按钮
    0.07
    爱的
    0.07
    Activations Density 0.010%

    No Known Activations