© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78775
    Prev
    Next
    INDEX
    Explanations

    taunt

    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
     Nahrung
    -0.08
    協
    -0.07
    width
    -0.07
    .width
    -0.07
    brtc
    -0.07
     collagen
    -0.07
     Transl
    -0.07
    -admin
    -0.07
    .transactions
    -0.07
     Jú
    -0.07
    POSITIVE LOGITS
     provoke
    0.10
     provocative
    0.09
     provoc
    0.09
     provoking
    0.09
     psic
    0.09
    zado
    0.08
     provocar
    0.08
     sorties
    0.08
     spirited
    0.08
    /prom
    0.08
    Activations Density 0.008%

    No Known Activations