© 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. 6063
    Prev
    Next
    INDEX
    Explanations

    micro

    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
    绑定
    -0.11
    LEBeta
    -0.09
    _ENDPOINT
    -0.09
     Buying
    -0.09
     eigenaar
    -0.09
    Bindable
    -0.09
    /:
    -0.09
    +i
    -0.08
     Endpoint
    -0.08
    ικών
    -0.08
    POSITIVE LOGITS
    cos
    0.15
    ptic
    0.11
    te
    0.10
    verse
    0.10
    gravity
    0.10
    _cos
    0.10
    collision
    0.09
    an
    0.09
    cl
    0.09
     cosm
    0.09
    Activations Density 0.006%

    No Known Activations