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. 30708
    Prev
    Next
    INDEX
    Explanations

    common words

    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
    soe
    -0.08
    ("//
    -0.08
     cest
    -0.07
    issues
    -0.07
    	c
    -0.07
    Issue
    -0.07
     issue
    -0.07
    	game
    -0.07
    g
    -0.07
    ('//
    -0.07
    POSITIVE LOGITS
     ohere
    0.11
     kepada
    0.11
     impetus
    0.10
     makeover
    0.10
     अधिकार
    0.10
     возможность
    0.10
     amandla
    0.10
     मौका
    0.09
     autonomy
    0.09
     шанс
    0.09
    Activations Density 0.168%

    No Known Activations