© 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. 3-RESID-POST-AA
    11. 2637
    Prev
    Next
    INDEX
    Explanations

    me

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بمع
    -0.08
    ктер
    -0.07
     Аб
    -0.07
     aba
    -0.07
     enacted
    -0.07
     Aber
    -0.07
    uk
    -0.07
     Wer
    -0.07
     locom
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     Shaun
    0.08
     Megan
    0.08
    _LINK
    0.08
    unchecked
    0.08
     Linda
    0.07
    dam
    0.07
     싸
    0.07
     муҳим
    0.07
     presto
    0.07
     Amy
    0.07
    Activations Density 0.006%

    No Known Activations