© 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. 620
    Prev
    Next
    INDEX
    Explanations

    along

    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
     accol
    -0.09
     umgehen
    -0.08
    천
    -0.08
     lenta
    -0.08
     لدى
    -0.07
    ausa
    -0.07
    deal
    -0.07
    λι
    -0.07
    Flood
    -0.07
     റെ
    -0.07
    POSITIVE LOGITS
    /of
    0.10
    shore
    0.10
     axis
    0.08
     Haitian
    0.08
    0.08
    .Pl
    0.08
     inc
    0.08
    ್ವ
    0.07
    .Parcel
    0.07
    lant
    0.07
    Activations Density 0.030%
    No Known Activations