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. 113917
    Prev
    Next
    INDEX
    Explanations

    Slack

    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
     juicy
    -0.08
    ğ
    -0.08
     DVD
    -0.08
    (JNIEnv
    -0.08
     Iraqi
    -0.07
     Taw
    -0.07
     rip
    -0.07
     IELTS
    -0.07
    ctime
    -0.07
     automobiles
    -0.07
    POSITIVE LOGITS
    Slack
    0.09
     compartment
    0.09
    Teams
    0.08
     че
    0.08
     Workspace
    0.08
     toplant
    0.08
     tek
    0.08
    stash
    0.08
    chein
    0.07
     чат
    0.07
    Activations Density 0.004%

    No Known Activations