Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11723
    Prev
    Next
    INDEX
    Explanations

    sequence

    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
    opro
    -0.09
     @_
    -0.08
    .expand
    -0.08
    expand
    -0.08
     handwriting
    -0.08
    -0.07
     sui
    -0.07
     Reform
    -0.07
     určit
    -0.07
     burocr
    -0.07
    POSITIVE LOGITS
     secund
    0.08
    ّر
    0.08
     ಉತ್ತ
    0.08
     UIColor
    0.08
     asteroid
    0.07
     centros
    0.07
    -anchor
    0.07
     asal
    0.07
    	DWORD
    0.07
     utama
    0.07
    Activations Density 0.002%

    No Known Activations