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. 88227
    Prev
    Next
    INDEX
    Explanations

    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
     of
    -0.08
     astronom
    -0.07
    fte
    -0.07
     in
    -0.06
     Sachsen
    -0.06
    .Invariant
    -0.06
    ுள
    -0.06
     equally
    -0.06
    ได้
    -0.06
     skut
    -0.06
    POSITIVE LOGITS
    宣布
    0.10
     finalizar
    0.09
     Deletes
    0.09
     permanecer
    0.09
     चै
    0.09
     prematurely
    0.09
    -remove
    0.08
    -turn
    0.08
    entermine
    0.08
     घोषित
    0.08
    Activations Density 0.001%

    No Known Activations