© 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. 75639
    Prev
    Next
    INDEX
    Explanations

    perfect

    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
     disappeared
    -0.08
     exting
    -0.07
     ',
    -0.07
    -0.07
    "When
    -0.07
     ::=
    -0.07
    ,”
    -0.07
     sont
    -0.07
    _fk
    -0.07
    _student
    -0.07
    POSITIVE LOGITS
    pickle
    0.08
    alyk
    0.08
    алам
    0.08
     उनका
    0.08
    sprek
    0.08
    াভ
    0.07
     upfront
    0.07
    sprekend
    0.07
    OUT
    0.07
     பார
    0.07
    Activations Density 0.000%
    No Known Activations