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. 48919
    Prev
    Next
    INDEX
    Explanations

    S

    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
     swapped
    -0.08
    ٰ
    -0.08
     likeness
    -0.08
     loosely
    -0.07
     glyph
    -0.07
     bildet
    -0.07
     replaced
    -0.07
     exchanged
    -0.07
     investering
    -0.07
     shaft
    -0.07
    POSITIVE LOGITS
    subtract
    0.09
     Luciano
    0.09
     Så
    0.08
     milestones
    0.08
    registr
    0.08
    erges
    0.08
    records
    0.08
     Chapman
    0.08
     Dyson
    0.08
    _HISTORY
    0.08
    Activations Density 0.028%

    No Known Activations