© 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. 3-RESID-POST-AA
    11. 12745
    Prev
    Next
    INDEX
    Explanations

    payment models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rang
    -0.09
     skil
    -0.08
     precip
    -0.08
     Sofia
    -0.08
    zone
    -0.07
     gram
    -0.07
    Detalle
    -0.07
    �
    -0.07
    Innen
    -0.07
     ג
    -0.07
    POSITIVE LOGITS
     divul
    0.08
    .si
    0.08
    णी
    0.07
    -s
    0.07
    ARGS
    0.07
    -साथ
    0.07
    되는
    0.07
     adhesives
    0.07
    .LA
    0.07
    pm
    0.07
    Activations Density 0.007%

    No Known Activations