© 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. 68320
    Prev
    Next
    INDEX
    Explanations

    :

    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
     compounded
    -0.09
    ઈ
    -0.08
     manifestation
    -0.08
    ავ
    -0.08
     financially
    -0.07
     dada
    -0.07
    իզ
    -0.07
    န
    -0.07
     Salamanca
    -0.07
    (",",
    -0.07
    POSITIVE LOGITS
     Pil
    0.08
     Paging
    0.08
     butterfly
    0.08
    蝶
    0.08
     Butterfly
    0.07
     Kow
    0.07
    Pil
    0.07
    Parcelable
    0.07
     president
    0.07
     Pilot
    0.07
    Activations Density 0.029%

    No Known Activations