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. 78527
    Prev
    Next
    INDEX
    Explanations

    code/logic

    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
    _pre
    -0.08
     sandstone
    -0.08
     scrub
    -0.07
     preco
    -0.07
     ọsọ
    -0.07
    Thin
    -0.07
    gea
    -0.07
    ғир
    -0.07
     alguém
    -0.07
    (root
    -0.07
    POSITIVE LOGITS
     _$
    0.08
    	comp
    0.08
    +D
    0.08
     bells
    0.08
    	Get
    0.08
     Yon
    0.07
     Zav
    0.07
     projected
    0.07
     projection
    0.07
     complication
    0.07
    Activations Density 0.000%

    No Known Activations