© 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. 23-RESID-POST-AA
    11. 47985
    Prev
    Next
    INDEX
    Explanations

    Di

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raça
    -0.08
    niają
    -0.08
    taí
    -0.08
     simplic
    -0.08
     全球
    -0.08
    _DI
    -0.08
    orsz
    -0.07
     sembr
    -0.07
     CSR
    -0.07
     SIGN
    -0.07
    POSITIVE LOGITS
    oph
    0.28
    ophysical
    0.15
    ophile
    0.14
    ophage
    0.14
    ophageal
    0.13
    оф
    0.13
    ophy
    0.13
    opher
    0.12
    ોફ
    0.12
    ophe
    0.11
    Activations Density 0.001%

    No Known Activations