Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 26720
    Prev
    Next
    INDEX
    Explanations

    toxicity levels

    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
    .empty
    -0.09
     SSL
    -0.08
    _SSL
    -0.08
     agendas
    -0.08
     metro
    -0.08
    -empty
    -0.08
     доволь
    -0.08
     satisfe
    -0.08
     pund
    -0.07
     thanking
    -0.07
    POSITIVE LOGITS
     lethal
    0.15
     hazardous
    0.15
     toxicity
    0.14
     dosage
    0.13
     poisoning
    0.12
     overdose
    0.12
     dose
    0.12
     incapac
    0.12
     হত্যা
    0.12
     intox
    0.12
    Activations Density 0.015%

    No Known Activations