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. 15-RESID-POST-AA
    6. 19071
    Prev
    Next
    INDEX
    Explanations

    counters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Når
    -0.08
    December
    -0.08
    Lift
    -0.08
    Dub
    -0.08
    Higher
    -0.08
    Ammo
    -0.08
    Personally
    -0.07
    .Println
    -0.07
    ulle
    -0.07
     :).
    -0.07
    POSITIVE LOGITS
     challenge
    0.08
     fazendo
    0.08
    ಂಗಳ
    0.08
    ახელ
    0.08
    ajem
    0.07
     حجر
    0.07
    		 
    0.07
     aufspringen
    0.07
     *↵↵
    0.07
    ებებს
    0.07
    Activations Density 0.000%

    No Known Activations