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. 11922
    Prev
    Next
    INDEX
    Explanations

    Giza pyramids

    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
     investigative
    -0.09
    	items
    -0.08
     GTK
    -0.08
     đôi
    -0.08
     dispos
    -0.08
     soirées
    -0.08
     disposable
    -0.08
     gramos
    -0.08
    	memcpy
    -0.08
     "&
    -0.08
    POSITIVE LOGITS
     encarg
    0.08
     cone
    0.08
     Cannon
    0.08
    leistung
    0.08
    _CLUSTER
    0.08
     Cone
    0.08
     Eun
    0.08
     tether
    0.07
     Eisen
    0.07
     Gun
    0.07
    Activations Density 0.004%

    No Known Activations