© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 6201
    Prev
    Next
    INDEX
    Explanations

    Masking and embeddings

    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
    전자
    -0.08
    Jose
    -0.08
    _tel
    -0.08
     kabel
    -0.08
     foran
    -0.08
    isering
    -0.08
    キ
    -0.08
    sticky
    -0.08
     Targets
    -0.08
     tel
    -0.08
    POSITIVE LOGITS
    #m
    0.08
    $m
    0.08
    Mask
    0.08
    MASK
    0.08
     mask
    0.07
    $s
    0.07
    .free
    0.07
    สน
    0.07
    (mask
    0.07
     compliments
    0.07
    Activations Density 0.001%

    No Known Activations