© 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. 99404
    Prev
    Next
    INDEX
    Explanations

    Tune and Pitch

    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
     packed
    -0.08
     hippoc
    -0.08
     Dreams
    -0.08
     grazing
    -0.08
     footsteps
    -0.08
     handgun
    -0.08
    ی
    -0.08
     Swansea
    -0.08
     thighs
    -0.08
     claw
    -0.08
    POSITIVE LOGITS
     alignment
    0.10
    Alignment
    0.10
    accur
    0.10
    accuracy
    0.09
    Align
    0.09
    alignment
    0.09
    校
    0.09
     Alignment
    0.09
     calibr
    0.09
    align
    0.09
    Activations Density 0.014%

    No Known Activations