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. 54106
    Prev
    Next
    INDEX
    Explanations

    Advice, instructions, or warnings

    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
     lach
    -0.08
    Used
    -0.08
    (close
    -0.07
     used
    -0.07
    Vir
    -0.07
     axial
    -0.07
    jected
    -0.07
     contrasts
    -0.07
    (named
    -0.07
     Used
    -0.07
    POSITIVE LOGITS
     לפני
    0.11
     먼저
    0.11
     before
    0.10
     eerst
    0.10
     terlebih
    0.10
     ennen
    0.10
     BEFORE
    0.10
     voordat
    0.10
     esclarecer
    0.10
     abans
    0.10
    Activations Density 0.070%

    No Known Activations