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. 44268
    Prev
    Next
    INDEX
    Explanations

    Locke

    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
     chant
    -0.08
     tuot
    -0.08
     menuju
    -0.08
    koch
    -0.08
     purge
    -0.08
     chanting
    -0.08
     materiał
    -0.08
     nära
    -0.07
     ליצור
    -0.07
     પુ
    -0.07
    POSITIVE LOGITS
     distinction
    0.08
     oils
    0.07
    ffic
    0.07
     Romney
    0.07
     allergic
    0.07
    icular
    0.07
    .defaults
    0.07
    .onload
    0.07
     differentiation
    0.07
     ?:
    0.07
    Activations Density 0.002%

    No Known Activations