© 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. 2617
    Prev
    Next
    INDEX
    Explanations

    comment

    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
     loto
    -0.08
     actor
    -0.08
     dwelling
    -0.08
     brace
    -0.08
    Tpl
    -0.08
     firstly
    -0.08
     affine
    -0.08
     TEN
    -0.08
    पति
    -0.08
     Bols
    -0.07
    POSITIVE LOGITS
    attle
    0.10
     Moodle
    0.07
     бірге
    0.07
    /o
    0.07
     کردن
    0.07
    _low
    0.07
     ચર્ચ
    0.07
    oje
    0.07
    \\
    0.07
    edu
    0.07
    Activations Density 0.000%

    No Known Activations