© 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. 6071
    Prev
    Next
    INDEX
    Explanations

    equals sign

    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
     quelles
    -0.09
    xido
    -0.09
    xae
    -0.08
    xbc
    -0.08
    xcf
    -0.08
    +x
    -0.08
    z
    -0.08
    -x
    -0.08
    xref
    -0.08
     quels
    -0.08
    POSITIVE LOGITS
     slope
    0.18
     m
    0.15
     slopes
    0.14
    Slope
    0.14
     rise
    0.14
    _gradient
    0.13
     pente
    0.13
     Rise
    0.12
    m
    0.12
    )m
    0.12
    Activations Density 0.056%

    No Known Activations