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. 102824
    Prev
    Next
    INDEX
    Explanations

    apex

    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
     adopter
    -0.08
     adop
    -0.08
    লো
    -0.08
     acknowledges
    -0.07
     particulier
    -0.07
     empirical
    -0.07
     acknowledging
    -0.07
    Gas
    -0.07
     Squares
    -0.07
     empir
    -0.07
    POSITIVE LOGITS
     apex
    0.10
     مخروط
    0.09
     tall
    0.09
     alc
    0.09
    顶部
    0.08
     pitched
    0.08
    andescent
    0.08
     graded
    0.08
     grading
    0.08
     Tall
    0.08
    Activations Density 0.010%

    No Known Activations