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. 119749
    Prev
    Next
    INDEX
    Explanations

    d

    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
    åk
    -0.08
    ===
    -0.08
     mynd
    -0.08
     där
    -0.08
     Sim
    -0.08
     হিস
    -0.07
     sims
    -0.07
     perfectly
    -0.07
     форме
    -0.07
     forgiving
    -0.07
    POSITIVE LOGITS
     orthopedic
    0.08
    542
    0.08
    -era
    0.07
    案件
    0.07
    -century
    0.07
     oprav
    0.07
     außer
    0.07
     pove
    0.07
    (exc
    0.07
     Brace
    0.07
    Activations Density 0.000%

    No Known Activations