Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78628
    Prev
    Next
    INDEX
    Explanations

    time

    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
     wise
    -0.08
     ಸಮಯ
    -0.08
     الوقت
    -0.08
    탄
    -0.07
    োদ
    -0.07
    дат
    -0.07
    ное
    -0.07
     cuantos
    -0.07
     frequência
    -0.07
    duled
    -0.07
    POSITIVE LOGITS
    /member
    0.08
    _Record
    0.08
    .commun
    0.08
    0.08
    /report
    0.08
    233
    0.08
    、中国
    0.07
     Folge
    0.07
    _MEMBER
    0.07
    .goto
    0.07
    Activations Density 0.026%

    No Known Activations