© 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. 48074
    Prev
    Next
    INDEX
    Explanations

    noct

    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
     horrific
    -0.08
     fake
    -0.08
     Städten
    -0.08
    社会主义
    -0.08
    Fans
    -0.08
    fiya
    -0.08
    ATOR
    -0.07
     zai
    -0.07
     cities
    -0.07
    фиц
    -0.07
    POSITIVE LOGITS
    urnal
    0.20
    urne
    0.16
    urn
    0.13
    il
    0.10
    urno
    0.10
    урнал
    0.09
    ambul
    0.09
    uria
    0.09
    urna
    0.09
     Wander
    0.09
    Activations Density 0.001%

    No Known Activations