Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112055
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _HEIGHT
    -0.08
     Heights
    -0.07
    HEIGHT
    -0.07
     Temper
    -0.07
    	height
    -0.07
    _BT
    -0.07
     recuerdo
    -0.07
     lasten
    -0.07
     distinta
    -0.07
    AH
    -0.07
    POSITIVE LOGITS
     ~/.
    0.08
     ~
    0.08
     👉
    0.08
    ిగ
    0.08
     {$
    0.08
     escrow
    0.08
     koju
    0.07
     flo
    0.07
    Usd
    0.07
    ."/
    0.07
    Activations Density 0.003%

    No Known Activations