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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130730
    Prev
    Next
    INDEX
    Explanations

    the letter f

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    folder
    -0.10
     fungsi
    -0.10
    _f
    -0.10
     filmed
    -0.10
     fáa
    -0.09
     فول
    -0.09
    ոֆ
    -0.09
     fumana
    -0.09
     funzione
    -0.09
     fuzzy
    -0.09
    POSITIVE LOGITS
    ocusing
    0.14
    urther
    0.14
    ollower
    0.12
    OCUS
    0.11
    uchsia
    0.11
    ollows
    0.11
    eture
    0.11
    ichier
    0.11
    eyn
    0.11
    ermi
    0.11
    Activations Density 0.656%

    No Known Activations