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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 61041
    Prev
    Next
    INDEX
    Explanations

    that

    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
     hashtag
    -0.08
     tolerate
    -0.07
     Tok
    -0.07
     workload
    -0.07
    (auth
    -0.07
    உ
    -0.07
    PE
    -0.07
    						 
    -0.07
    ik
    -0.07
    Dialog
    -0.07
    POSITIVE LOGITS
     unsettling
    0.10
    提醒
    0.10
     delight
    0.10
     Delight
    0.09
    แทง
    0.09
     delights
    0.09
     ليلة
    0.09
     presque
    0.09
     Sgt
    0.08
     چاروا
    0.08
    Activations Density 0.032%

    No Known Activations