© 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. 48175
    Prev
    Next
    INDEX
    Explanations

    ót

    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
    ке
    -0.09
    кой
    -0.08
    stack
    -0.07
     stack
    -0.07
    -medium
    -0.07
    pal
    -0.07
    (strings
    -0.07
    (stack
    -0.07
    _apps
    -0.07
    -0.07
    POSITIVE LOGITS
    eles
    0.09
    �
    0.08
    στ
    0.08
    国
    0.08
     �
    0.08
     πολι
    0.08
     Barça
    0.08
    ασ
    0.08
     garis
    0.08
    ્વ
    0.08
    Activations Density 0.000%
    No Known Activations