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. 78616
    Prev
    Next
    INDEX
    Explanations

    mentioning something

    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
    ailability
    -0.08
     Outcomes
    -0.08
     Summit
    -0.08
     Mana
    -0.08
     Worker
    -0.07
    Dash
    -0.07
    [^
    -0.07
    _wait
    -0.07
     ✅
    -0.07
     Outcome
    -0.07
    POSITIVE LOGITS
     topics
    0.11
     topic
    0.11
     nostalgic
    0.11
     тему
    0.11
     reminis
    0.10
    .topic
    0.10
     вдруг
    0.10
     mentions
    0.10
     mentioning
    0.10
     inadvertently
    0.10
    Activations Density 0.107%

    No Known Activations