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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 58877
    Prev
    Next
    INDEX
    Explanations

    needle

    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
    -0.08
     sâu
    -0.07
     citizen
    -0.07
     mod
    -0.07
    Tunes
    -0.07
    oss
    -0.07
     citizens
    -0.07
     winds
    -0.07
     me
    -0.07
     logout
    -0.07
    POSITIVE LOGITS
     അപേക്ഷ
    0.09
    ു�
    0.08
     INSERT
    0.07
    	Hash
    0.07
     adviser
    0.07
     നേത
    0.07
     വിഭാഗ
    0.07
    ISTA
    0.07
    姑娘
    0.07
     আন
    0.07
    Activations Density 0.000%

    No Known Activations