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. 103151
    Prev
    Next
    INDEX
    Explanations

    :

    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
     sérieux
    -0.08
    sweet
    -0.08
     sweet
    -0.07
     Valentine's
    -0.07
    piece
    -0.07
     emph
    -0.07
     behandelt
    -0.07
     wedges
    -0.07
     vitamines
    -0.07
     deficiencies
    -0.07
    POSITIVE LOGITS
     ilimit
    0.09
     subprocess
    0.08
    Indices
    0.08
     zpr
    0.08
     separar
    0.07
     baada
    0.07
    onda
    0.07
     notifying
    0.07
     bob
    0.07
     unlimited
    0.07
    Activations Density 0.218%

    No Known Activations