© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54891
    Prev
    Next
    INDEX
    Explanations

    null terminator

    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
     procure
    -0.10
     procurement
    -0.09
    _ssl
    -0.09
     Rid
    -0.08
    -credit
    -0.08
     lobby
    -0.08
    :mm
    -0.08
    _credit
    -0.08
     lounge
    -0.08
    -weather
    -0.08
    POSITIVE LOGITS
     termination
    0.11
     terminating
    0.10
    Termination
    0.10
     terminated
    0.09
     termin
    0.09
    termin
    0.09
     terminate
    0.09
     cease
    0.09
    termination
    0.09
     trailing
    0.09
    Activations Density 0.003%

    No Known Activations