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. 65801
    Prev
    Next
    INDEX
    Explanations

    marketing services

    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
    さて
    -0.08
     союз
    -0.08
     cherish
    -0.08
     oplysninger
    -0.07
    _CHAR
    -0.07
    Cep
    -0.07
     hint
    -0.07
    VALUES
    -0.07
     cep
    -0.07
     advent
    -0.07
    POSITIVE LOGITS
     консульта
    0.10
     turnkey
    0.10
    드립니다
    0.09
     bespoke
    0.09
     expertly
    0.09
     consultancy
    0.09
     danış
    0.09
     konusunda
    0.09
    beratung
    0.08
     करण्यात
    0.08
    Activations Density 0.157%

    No Known Activations