© 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. 5881
    Prev
    Next
    INDEX
    Explanations

    Password

    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
     porcent
    -0.08
    reas
    -0.08
    Trademark
    -0.08
     underline
    -0.08
     wallpapers
    -0.08
     commercials
    -0.08
    County
    -0.08
     Trademark
    -0.07
    \Category
    -0.07
    percentage
    -0.07
    POSITIVE LOGITS
    	has
    0.14
    (has
    0.13
    Has
    0.13
    .has
    0.12
     Has
    0.12
    _digest
    0.11
    _hash
    0.11
    Hash
    0.11
    _DIG
    0.10
    _HASH
    0.10
    Activations Density 0.001%

    No Known Activations