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. 58737
    Prev
    Next
    INDEX
    Explanations

    attributing causes

    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
    dead
    -0.08
    charged
    -0.08
    	l
    -0.08
     anderer
    -0.07
    neu
    -0.07
    VO
    -0.07
     capable
    -0.07
    male
    -0.07
     dead
    -0.07
    ith
    -0.07
    POSITIVE LOGITS
     solace
    0.08
     عليك
    0.08
     drank
    0.08
     поход
    0.08
     hoof
    0.07
     честь
    0.07
     фигур
    0.07
     puesta
    0.07
     վրա
    0.07
     avr
    0.07
    Activations Density 0.044%

    No Known Activations