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

    Neuronpedia

    APICircuit 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. 88237
    Prev
    Next
    INDEX
    Explanations

    F.A.Q.s

    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
    inden
    -0.08
    	from
    -0.08
    same
    -0.08
    imde
    -0.08
    appear
    -0.08
     Valve
    -0.07
    	errors
    -0.07
     versehen
    -0.07
    	gl
    -0.07
     indications
    -0.07
    POSITIVE LOGITS
     사용할
    0.09
     ()
    0.08
    Стоимость
    0.08
     deployment
    0.07
    Six
    0.07
     Norris
    0.07
    Cuál
    0.07
     wak
    0.07
    tras
    0.07
     Six
    0.07
    Activations Density 0.058%

    No Known Activations