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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 48301
    Prev
    Next
    INDEX
    Explanations

    Circumference of shapes

    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
    iają
    -0.08
     Roe
    -0.08
     lif
    -0.08
     zol
    -0.08
     piet
    -0.08
     yaş
    -0.08
     թ
    -0.08
     signific
    -0.08
     ಸಾವ
    -0.07
    osia
    -0.07
    POSITIVE LOGITS
    ference
    0.29
    FERENCE
    0.19
    ferencia
    0.19
    ferences
    0.17
    férence
    0.17
    stances
    0.15
    ферен
    0.14
    ferencing
    0.14
    ferenced
    0.14
    ferenz
    0.14
    Activations Density 0.003%

    No Known Activations