© 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. 65491
    Prev
    Next
    INDEX
    Explanations

    compliance

    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
     Bub
    -0.08
     Albion
    -0.08
    тоў
    -0.08
     anb
    -0.07
    _USERS
    -0.07
     homo
    -0.07
     каб
    -0.07
     Giovanni
    -0.07
     Hogwarts
    -0.07
     ancient
    -0.07
    POSITIVE LOGITS
     determinants
    0.10
     показатели
    0.10
    cline
    0.09
    isti
    0.09
     monitor
    0.08
    -related
    0.08
     indikator
    0.08
     പരിശോധ
    0.08
     개선
    0.08
    Criterion
    0.08
    Activations Density 0.086%

    No Known Activations