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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 71306
    Prev
    Next
    INDEX
    Explanations

    environmental destruction

    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
    IME
    -0.10
    556
    -0.08
    @property
    -0.08
    Responses
    -0.08
     приглаш
    -0.08
    (seconds
    -0.08
     Dice
    -0.08
    Dice
    -0.08
     Keep
    -0.07
    骰
    -0.07
    POSITIVE LOGITS
    造成
    0.12
     irresponsible
    0.11
     exacerb
    0.11
     verurs
    0.11
     accumulation
    0.10
    殖
    0.10
    导致
    0.10
     devastation
    0.10
    loss
    0.10
     prácticas
    0.10
    Activations Density 0.041%

    No Known Activations