© 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. 99389
    Prev
    Next
    INDEX
    Explanations

    Redis replication and slaves

    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
    -last
    -0.09
     esper
    -0.08
    ード
    -0.08
    _EXPECT
    -0.08
    _last
    -0.08
    -img
    -0.07
    _evt
    -0.07
     bienes
    -0.07
     island
    -0.07
     mwisho
    -0.07
    POSITIVE LOGITS
    entionally
    0.08
     autos
    0.07
     ಕಾರ್ಯ
    0.07
    panelen
    0.07
     Michaels
    0.07
     Blue
    0.07
     accueill
    0.07
    baud
    0.07
    Solar
    0.07
    .ax
    0.07
    Activations Density 0.001%

    No Known Activations