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. 58837
    Prev
    Next
    INDEX
    Explanations

    self-harm and suicide

    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
     cumin
    -0.08
     parity
    -0.08
     Req
    -0.08
     Ethernet
    -0.08
     grammar
    -0.08
    ตำ
    -0.08
     ovens
    -0.08
     ભૂ
    -0.08
     regio
    -0.07
    osition
    -0.07
    POSITIVE LOGITS
     suicidal
    0.17
     suic
    0.15
     suicide
    0.15
     Suicide
    0.13
     homic
    0.11
     despair
    0.11
     antidepress
    0.10
     poign
    0.10
     траг
    0.10
     tragedies
    0.10
    Activations Density 0.054%

    No Known Activations