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. 106183
    Prev
    Next
    INDEX
    Explanations

    игру

    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
     experimented
    -0.09
    �
    -0.08
     harmonious
    -0.08
    kundige
    -0.07
     dissect
    -0.07
    �
    -0.07
    ’entretien
    -0.07
     experimentally
    -0.07
    ("@
    -0.07
    ේ
    -0.07
    POSITIVE LOGITS
    ühlen
    0.08
    okia
    0.08
     pagl
    0.08
    	params
    0.08
    _fake
    0.08
    ook
    0.08
     Hemisphere
    0.08
     Embedded
    0.08
    ogel
    0.07
    _shell
    0.07
    Activations Density 0.003%

    No Known Activations