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. 58531
    Prev
    Next
    INDEX
    Explanations

    question punctuation

    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
    rä
    -0.07
    older
    -0.07
     puedo
    -0.07
     señala
    -0.07
    רא
    -0.07
    Align
    -0.07
    AMERA
    -0.07
     лев
    -0.07
     этаж
    -0.07
    助
    -0.07
    POSITIVE LOGITS
     unrestricted
    0.12
     limitless
    0.10
     unlimited
    0.10
     encompassing
    0.10
     arbitrary
    0.09
     unleashed
    0.08
     solange
    0.08
     വ്യാപ
    0.08
    ும்ப
    0.08
     permiss
    0.08
    Activations Density 0.081%

    No Known Activations